Methods › General › Large Batch Optimization

Large Batch Optimization

8 methods 1,257 papers tagged archive 2025-07-28

Stochastic Optimization methods are used to optimize neural networks. We typically take a mini-batch of data, hence 'stochastic', and perform a type of gradient descent with this minibatch. Below you can find a continuously updating list of stochastic optimization algorithms.

Methods

All 8 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.

Adafactor – 733
LAMB – 199
AdaGrad 2011 191
LARS – 77
1-bit Adam – 40
Nesterov Accelerated Gradient 1983 34
Distributed Shampoo – 5
SLAMB Sparse Layer-wise Adaptive Moments optimizer for large Batch training – 1